Template · AI Agents

AI Agent Specification Template

A fill-in specification for an autonomous agent — the task boundary, tool inventory with blast radius, stopping conditions, spend caps, human checkpoints and the log you will need when it does something surprising.

Markdown. No sign-up, no email.

An agent is a program that decides what to do next. Everything below exists because that sentence has consequences. Fill it in before the agent touches anything real — a blank cell here becomes an incident later, and the incident arrives with no record of what was intended.

Agent name: _______________ Owner (person, not team): _______________ Date: _______ Version: _______

1. The task#

One sentence, in the user's words: _______________

What it is explicitly NOT allowed to attempt: _______________

What a human does today instead, and how long it takes: _______________

If you cannot describe the task in one sentence, you have a workflow, not an agent task. Workflows are cheaper, more predictable, and easier to debug — build the workflow.

2. Autonomy level — pick one and record why#

LevelDescriptionChosen
0Suggests; a human performs every action
1Acts on reversible things; asks before anything else
2Acts within a stated budget and scope; reports after
3Acts continuously; a human reviews samples

Why this level: _______________ What would have to be true to move up one level: _______________

3. Tool inventory — the blast radius table#

Every tool the agent can call. Reversibility is the column that matters; fill it honestly.

ToolWhat it doesReversible?Worst realistic outcomeConfirmation required
yes / no
yes / no
yes / no

🔴 Any row with "no" in the reversible column and "none" in confirmation is the incident you will be writing up. Decide now, not then.

Tools deliberately withheld, and why: _______________

4. Stopping conditions#

An agent without stopping conditions does not fail — it loops, spends, and retries.

ConditionLimit
Maximum steps per task
Maximum wall-clock time
Maximum spend per task
Maximum spend per day (hard cap, enforced where?)
Repeated identical actionstop after ___
Repeated tool errorstop after ___
No measurable progressstop after ___ steps

Where each cap is enforced (in the agent's own logic is not sufficient — an agent can reason its way around its own instructions; the cap must sit in the layer the agent cannot edit): _______________

5. Human checkpoints#

TriggerWho is askedHow they are reachedWhat happens if nobody answers

The last column is the one teams skip. Silence must have a defined meaning: default-stop is almost always correct, and it must be written down.

6. Untrusted input#

Agents read things: web pages, documents, tickets, emails, tool output. All of it can contain instructions aimed at the agent.

Sources of text the agent will read
How retrieved content is delimited as data
Tools that can be triggered as a direct result of read content
What prevents a read instruction from becoming an action

🔴 The dangerous combination is: reads untrusted content and holds a tool with real-world effect and acts without confirmation. If all three are true, redesign rather than mitigate.

7. Memory and state#

What persists between runs
Who can write to that memory
How a poisoned or wrong memory is detected
How it is cleared

Memory that only ever accumulates will eventually contain something false, and the agent will treat it as established fact.

8. Observability#

Every tool call logged with argumentsyes / no
Reasoning/decision trace retainedyes / no
Retention period
Cost per task trackedyes / no
Where a human watches a run live
Alert on: cap hit, loop detected, tool error rate

Could you reconstruct, from logs alone, why the agent did something surprising three days ago? yes / no. If no, the observability is not finished.

9. Evaluation before release#

CheckResultDate
Runs on a fixed task set, results recorded
Behaviour when a tool fails
Behaviour when input is ambiguous
Behaviour when instructed by content it reads
Spend cap actually stops it (tested, not assumed)
Kill switch tested end to end

10. Sign-off#

NameDate
Built by
Security review
Budget owner
Approved to run unattended

Back to AI Agents